lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Wed, 3 Feb 2021 09:59:57 -0800
From:   Wei Wang <weiwan@...gle.com>
To:     Alexander Duyck <alexander.duyck@...il.com>
Cc:     David Miller <davem@...emloft.net>,
        Netdev <netdev@...r.kernel.org>,
        Jakub Kicinski <kuba@...nel.org>,
        Eric Dumazet <edumazet@...gle.com>,
        Paolo Abeni <pabeni@...hat.com>,
        Hannes Frederic Sowa <hannes@...essinduktion.org>,
        Felix Fietkau <nbd@....name>
Subject: Re: [PATCH net-next v9 2/3] net: implement threaded-able napi poll
 loop support

On Wed, Feb 3, 2021 at 9:20 AM Alexander Duyck
<alexander.duyck@...il.com> wrote:
>
> On Fri, Jan 29, 2021 at 10:22 AM Wei Wang <weiwan@...gle.com> wrote:
> >
> > This patch allows running each napi poll loop inside its own
> > kernel thread.
> > The kthread is created during netif_napi_add() if dev->threaded
> > is set. And threaded mode is enabled in napi_enable(). We will
> > provide a way to set dev->threaded and enable threaded mode
> > without a device up/down in the following patch.
> >
> > Once that threaded mode is enabled and the kthread is
> > started, napi_schedule() will wake-up such thread instead
> > of scheduling the softirq.
> >
> > The threaded poll loop behaves quite likely the net_rx_action,
> > but it does not have to manipulate local irqs and uses
> > an explicit scheduling point based on netdev_budget.
> >
> > Co-developed-by: Paolo Abeni <pabeni@...hat.com>
> > Signed-off-by: Paolo Abeni <pabeni@...hat.com>
> > Co-developed-by: Hannes Frederic Sowa <hannes@...essinduktion.org>
> > Signed-off-by: Hannes Frederic Sowa <hannes@...essinduktion.org>
> > Co-developed-by: Jakub Kicinski <kuba@...nel.org>
> > Signed-off-by: Jakub Kicinski <kuba@...nel.org>
> > Signed-off-by: Wei Wang <weiwan@...gle.com>
> > ---
> >  include/linux/netdevice.h |  21 +++----
> >  net/core/dev.c            | 117 ++++++++++++++++++++++++++++++++++++++
> >  2 files changed, 124 insertions(+), 14 deletions(-)
> >
> > diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> > index 02dcef4d66e2..f1e9fe9017ac 100644
> > --- a/include/linux/netdevice.h
> > +++ b/include/linux/netdevice.h
> > @@ -347,6 +347,7 @@ struct napi_struct {
> >         struct list_head        dev_list;
> >         struct hlist_node       napi_hash_node;
> >         unsigned int            napi_id;
> > +       struct task_struct      *thread;
> >  };
> >
> >  enum {
> > @@ -358,6 +359,7 @@ enum {
> >         NAPI_STATE_NO_BUSY_POLL,        /* Do not add in napi_hash, no busy polling */
> >         NAPI_STATE_IN_BUSY_POLL,        /* sk_busy_loop() owns this NAPI */
> >         NAPI_STATE_PREFER_BUSY_POLL,    /* prefer busy-polling over softirq processing*/
> > +       NAPI_STATE_THREADED,            /* The poll is performed inside its own thread*/
> >  };
> >
> >  enum {
> > @@ -369,6 +371,7 @@ enum {
> >         NAPIF_STATE_NO_BUSY_POLL        = BIT(NAPI_STATE_NO_BUSY_POLL),
> >         NAPIF_STATE_IN_BUSY_POLL        = BIT(NAPI_STATE_IN_BUSY_POLL),
> >         NAPIF_STATE_PREFER_BUSY_POLL    = BIT(NAPI_STATE_PREFER_BUSY_POLL),
> > +       NAPIF_STATE_THREADED            = BIT(NAPI_STATE_THREADED),
> >  };
> >
> >  enum gro_result {
> > @@ -503,20 +506,7 @@ static inline bool napi_complete(struct napi_struct *n)
> >   */
> >  void napi_disable(struct napi_struct *n);
> >
> > -/**
> > - *     napi_enable - enable NAPI scheduling
> > - *     @n: NAPI context
> > - *
> > - * Resume NAPI from being scheduled on this context.
> > - * Must be paired with napi_disable.
> > - */
> > -static inline void napi_enable(struct napi_struct *n)
> > -{
> > -       BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
> > -       smp_mb__before_atomic();
> > -       clear_bit(NAPI_STATE_SCHED, &n->state);
> > -       clear_bit(NAPI_STATE_NPSVC, &n->state);
> > -}
> > +void napi_enable(struct napi_struct *n);
> >
> >  /**
> >   *     napi_synchronize - wait until NAPI is not running
> > @@ -1826,6 +1816,8 @@ enum netdev_priv_flags {
> >   *
> >   *     @wol_enabled:   Wake-on-LAN is enabled
> >   *
> > + *     @threaded:      napi threaded mode is enabled
> > + *
> >   *     @net_notifier_list:     List of per-net netdev notifier block
> >   *                             that follow this device when it is moved
> >   *                             to another network namespace.
> > @@ -2143,6 +2135,7 @@ struct net_device {
> >         struct lock_class_key   *qdisc_running_key;
> >         bool                    proto_down;
> >         unsigned                wol_enabled:1;
> > +       unsigned                threaded:1;
> >
> >         struct list_head        net_notifier_list;
> >
> > diff --git a/net/core/dev.c b/net/core/dev.c
> > index 7d23bff03864..743dd69fba19 100644
> > --- a/net/core/dev.c
> > +++ b/net/core/dev.c
> > @@ -91,6 +91,7 @@
> >  #include <linux/etherdevice.h>
> >  #include <linux/ethtool.h>
> >  #include <linux/skbuff.h>
> > +#include <linux/kthread.h>
> >  #include <linux/bpf.h>
> >  #include <linux/bpf_trace.h>
> >  #include <net/net_namespace.h>
> > @@ -1493,6 +1494,37 @@ void netdev_notify_peers(struct net_device *dev)
> >  }
> >  EXPORT_SYMBOL(netdev_notify_peers);
> >
> > +static int napi_threaded_poll(void *data);
> > +
> > +static int napi_kthread_create(struct napi_struct *n)
> > +{
> > +       int err = 0;
> > +
> > +       /* Create and wake up the kthread once to put it in
> > +        * TASK_INTERRUPTIBLE mode to avoid the blocked task
> > +        * warning and work with loadavg.
> > +        */
> > +       n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
> > +                               n->dev->name, n->napi_id);
> > +       if (IS_ERR(n->thread)) {
> > +               err = PTR_ERR(n->thread);
> > +               pr_err("kthread_run failed with err %d\n", err);
> > +               n->thread = NULL;
> > +       }
> > +
> > +       return err;
> > +}
> > +
> > +static void napi_kthread_stop(struct napi_struct *n)
> > +{
> > +       if (!n->thread)
> > +               return;
> > +
> > +       kthread_stop(n->thread);
> > +       clear_bit(NAPI_STATE_THREADED, &n->state);
> > +       n->thread = NULL;
> > +}
> > +
>
> So I think the napi_kthread_stop should also be split into two parts
> and distributed between the napi_disable and netif_napi_del functions.
>
> We should probably be clearing the NAPI_STATE_THREADED bit in
> napi_disable, and freeing the thread in netif_napi_del.
>
> >  static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
> >  {
> >         const struct net_device_ops *ops = dev->netdev_ops;
> > @@ -4252,6 +4284,21 @@ int gro_normal_batch __read_mostly = 8;
> >  static inline void ____napi_schedule(struct softnet_data *sd,
> >                                      struct napi_struct *napi)
> >  {
> > +       struct task_struct *thread;
> > +
> > +       if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
> > +               /* Paired with smp_mb__before_atomic() in
> > +                * napi_enable(). Use READ_ONCE() to guarantee
> > +                * a complete read on napi->thread. Only call
> > +                * wake_up_process() when it's not NULL.
> > +                */
> > +               thread = READ_ONCE(napi->thread);
> > +               if (thread) {
> > +                       wake_up_process(thread);
> > +                       return;
> > +               }
> > +       }
> > +
> >         list_add_tail(&napi->poll_list, &sd->poll_list);
> >         __raise_softirq_irqoff(NET_RX_SOFTIRQ);
> >  }
> > @@ -6720,6 +6767,12 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
> >         set_bit(NAPI_STATE_NPSVC, &napi->state);
> >         list_add_rcu(&napi->dev_list, &dev->napi_list);
> >         napi_hash_add(napi);
> > +       /* Create kthread for this napi if dev->threaded is set.
> > +        * Clear dev->threaded if kthread creation failed so that
> > +        * threaded mode will not be enabled in napi_enable().
> > +        */
> > +       if (dev->threaded && napi_kthread_create(napi))
> > +               dev->threaded = 0;
> >  }
> >  EXPORT_SYMBOL(netif_napi_add);
> >
> > @@ -6734,12 +6787,31 @@ void napi_disable(struct napi_struct *n)
> >                 msleep(1);
> >
> >         hrtimer_cancel(&n->timer);
> > +       napi_kthread_stop(n);
> >
>
> So I think there may be an issue here since we had netif_napi_add
> create the thread, but you are freeing it in napi_kthread_stop if I am
> not mistaken. That is why I suggested making this only a clear_bit
> call like the ones below to just clear the threaded flag from the
> state.

Makes sense. I will split napi_kthread_stop().

>
> >         clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
> >         clear_bit(NAPI_STATE_DISABLE, &n->state);
> >  }
> >  EXPORT_SYMBOL(napi_disable);
> >
> > +/**
> > + *     napi_enable - enable NAPI scheduling
> > + *     @n: NAPI context
> > + *
> > + * Resume NAPI from being scheduled on this context.
> > + * Must be paired with napi_disable.
> > + */
> > +void napi_enable(struct napi_struct *n)
> > +{
> > +       BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
> > +       smp_mb__before_atomic();
> > +       clear_bit(NAPI_STATE_SCHED, &n->state);
> > +       clear_bit(NAPI_STATE_NPSVC, &n->state);
> > +       if (n->dev->threaded && n->thread)
> > +               set_bit(NAPI_STATE_THREADED, &n->state);
> > +}
> > +EXPORT_SYMBOL(napi_enable);
> > +
> >  static void flush_gro_hash(struct napi_struct *napi)
> >  {
> >         int i;
> > @@ -6862,6 +6934,51 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
> >         return work;
> >  }
> >
> > +static int napi_thread_wait(struct napi_struct *napi)
> > +{
> > +       set_current_state(TASK_INTERRUPTIBLE);
> > +
> > +       while (!kthread_should_stop() && !napi_disable_pending(napi)) {
> > +               if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
> > +                       WARN_ON(!list_empty(&napi->poll_list));
> > +                       __set_current_state(TASK_RUNNING);
> > +                       return 0;
> > +               }
> > +
> > +               schedule();
> > +               set_current_state(TASK_INTERRUPTIBLE);
> > +       }
> > +       __set_current_state(TASK_RUNNING);
> > +       return -1;
> > +}
> > +
> > +static int napi_threaded_poll(void *data)
> > +{
> > +       struct napi_struct *napi = data;
> > +       void *have;
> > +
> > +       while (!napi_thread_wait(napi)) {
> > +               for (;;) {
> > +                       bool repoll = false;
> > +
> > +                       local_bh_disable();
> > +
> > +                       have = netpoll_poll_lock(napi);
> > +                       __napi_poll(napi, &repoll);
> > +                       netpoll_poll_unlock(have);
> > +
> > +                       __kfree_skb_flush();
> > +                       local_bh_enable();
> > +
> > +                       if (!repoll)
> > +                               break;
> > +
> > +                       cond_resched();
> > +               }
> > +       }
> > +       return 0;
> > +}
> > +
> >  static __latent_entropy void net_rx_action(struct softirq_action *h)
> >  {
> >         struct softnet_data *sd = this_cpu_ptr(&softnet_data);
> > --
> > 2.30.0.365.g02bc693789-goog
> >

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ